sima_atlas: Instructions file for Codex

AGENTS.md

sima_atlas AGENTS.md is an instructions file for Codex, OpenCode from neskuchny/sima_atlas. It costs 1,158 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working in neskuchny/sima_atlas. They explain that a block is a directory of contract files describing a feature, rather than ordinary source code alone.

In plain words
What is it for?
Use them when working in the Sima Atlas repository to find the canonical navigation guide, inspect a block’s purpose and acceptance requirements, review dependencies and history, and follow project-specific rules.
Why use it?
They give agents a fixed reading order and warn them to respect recorded constraints and past architectural decisions. This helps avoid making changes without understanding the project’s contracts.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is neskuchny/sima_atlas's own configuration. It tells Codex and OpenCode how to work on sima_atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sima_atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to neskuchny/sima_atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/neskuchny/sima_atlas/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/neskuchny/sima_atlas

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sima_atlas AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/neskuchny/sima_atlas/agents-md.svg)](https://agentmods.dev/instructions/neskuchny/sima_atlas/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/neskuchny/sima_atlas/agents-md"><img src="https://agentmods.dev/badge/instructions/neskuchny/sima_atlas/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,158 This file is loaded in full into every session.
When invoked 1,158 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01158 $0.01158
Opus 5 $0.00579 $0.00579
Sonnet 5 $0.00232 $0.00232
Haiku 4.5 $0.00116 $0.00116

Measured 7d ago against content hash ab09f9c8aa1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sima_atlas AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents working in this repo

If you're an AI coding agent (Claude Code / Cursor / Codex / Aider / custom) operating in a Sima Atlas codebase, read docs/agent-navigation.md first. That document is the canonical strategy for how to traverse this repo economically — read order, MCP tool selection, skip-list, write protocol, stop-signals.

Quick contract (full version in agent-navigation.md)

  1. Block = directory of contracts, not code. Each block is atlas/blocks/<id>/ containing mission.md, kpi.md, acceptance.md, depends_on.md, provides.md, tasks.md, files.md, code_summary.md, checks.log. Multi-tenant: atlas/clients/<client>/blocks/<id>/.

  2. Read mission before code. Standard order: /atlas/project.md/atlas/rules.md → tech_stack → mission → acceptance → depends_on → (deps' provides) → tasks → narrative.md → decisions.log → checks.log → operator_profile/dont_use+always_use. Stop at the first level that answers the question. The last four are the memory layer (R-7.76+) — they tell you what was tried, rejected, and locked-in by the operator. Never reverse past decisions without explicit operator override.

    When invoked through run_block_implementation.mjs, all of the above is pre-injected into your prompt under «## ⚠ Block memory» — don't re-fetch.

  3. Use MCP tools, not Read, when available. Sima registers ~70 tools via .mcp.json (Claude Code auto-detects; for Cursor/others see docs/integrations.md). The five you'll need most: read_block, list_dependencies, update_block, verify_block_acceptance, sync_check. To grow a block's memory from a chat, use build_context_pack for input, and enqueue_ingestion / ingest_chat_distillate to write distilled insights into decisions.log / patterns.md (the memory pipeline).

  4. Skip-list — never auto-read these: atlas/llm_traces/, atlas/run_logs/, atlas/run_state/, atlas/acceptance_runs/, atlas/process_runs/, atlas/eval_history/, atlas/operator_profile/, atlas/proposals/ (use accept_proposal MCP tool), atlas/context_packs/ (use build_context_pack MCP tool), node_modules/, archive/, test-results/.

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 88 lines · 1,158 tokens per session scan A ab09f9c8aa1c

Subscribe to this mod's changes

sima_atlas AGENTS.md is an instructions file published in the GitHub repository neskuchny/sima_atlas (6 stars, last pushed 2mo ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0058 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens